Search results

This paper aims to review in-memory computing (IMC) for machine learning (ML) applications from history, architectures and options aspects. In this review, the authors investigate different architectural aspects and collect and provide our comparative evaluations.

Collecting over 40 IMC papers related to hardware design and optimization techniques of recent years, then classify them into three optimization option categories: optimization through graphic processing unit (GPU), optimization through reduced precision and optimization through hardware accelerator. Then, the authors brief those techniques in aspects such as what kind of data set it applied, how it is designed and what is the contribution of this design.

ML algorithms are potent tools accommodated on IMC architecture. Although general-purpose hardware (central processing units and GPUs) can supply explicit solutions, their energy efficiencies have limitations because of their excessive flexibility support. On the other hand, hardware accelerators (field programmable gate arrays and application-specific integrated circuits) win on the energy efficiency aspect, but individual accelerator often adapts exclusively to ax single ML approach (family). From a long hardware evolution perspective, hardware/software collaboration heterogeneity design from hybrid platforms is an option for the researcher.

IMC’s optimization enables high-speed processing, increases performance and analyzes massive volumes of data in real-time. This work reviews IMC and its evolution. Then, the authors categorize three optimization paths for the IMC architecture to improve performance metrics.

This study aims to investigate the consumer behavior toward telemedicine services in India during the COVID-19 pandemic onset. With lockdown restrictions and safety concerns in visiting brick-and-mortar clinics or hospitals during the pandemic, Telemedicine had emerged as a potent alternative for seeking redressal to health issues. Based on theory and focus interviews with the telemedicine users, the researchers proposed a model to understand the intent and actual usage of telemedicine in India.

The cross-sectional study undertaken used a questionnaire designed on a seven-point Likert scale and administered to respondents with the objective of identifying the determinants of intent and actual usage of telemedicine services. Simple random sampling was used to collect primary data. The data was cleaned and finally a sample of 405 responses complete in all respects was considered for analysis. The questionnaire comprised of 34 items and following the recommendation of Hair et al. (2016), which says the minimum sample size in structural equation modeling should be ten times the number of indicator variables, a sample size of 405 was deemed adequate.

The research paper finds that performance expectancy, attitude, credibility and self-efficacy positively impact the intention of consumers to use telemedicine services. As the effort expectancy or risk perception toward telemedicine increases the intent and actual usage of telemedicine decreases. The intention to use telemedicine emerged as a strong predictor of the actual usage of telemedicine. Intent to use telemedicine was explained 81.4% by its predictors of performance expectancy, effort expectancy, attitude, risk, credibility and self-efficacy, and actual usage was explained 79.9% by its predictors. This study also reports that telemedicine was found to be popular among chronic as well as episodic patients though the preference was skewed in favor of the episodic patients. One of the advantages of telemedicine is its availability round the clock, and the study found that 8 a. m. to 12 noon time slot as the most preferred slot for seeking telemedicine services.

Chang (2004) opined that telemedicine can fulfill the needs of all stakeholders: citizens, health-care consumers, medical doctors and health-care professionals, policymakers, and so on. Considering the promise telemedicine holds, this realm must be studied and leveraged to the full potential. The study found that patients were using telemedicine even for their day-to-day aliments. This indicates a growing popularity of telemedicine and as such an opportunity for telemedicine companies to leverage it. In India, pharmaceutical companies cannot give commercial advertisements for medicines, and the same can only be sold through a registered medical practitioner’s prescription. As such there is total dependency on the medical practitioner for the sale of medicines. Telemedicine companies offer services of home delivering medicines clubbed with medical consultation thus giving them forward integration in their business models. Using telemedicine the patients had control over the timings of the services offered, and as such the waiting time to get a consultation and subsequent treatment was reduced considerably. Best medical advice from across the globe is available to the patient at less cost. Medical practitioners also stand to benefit as they can treat a variety of cases, collaborate among the medical fraternity and give consultation safely in case of fatal contagious diseases.

This study points to a definite growing popularity of telemedicine services not only in episodic patients but also chronic patients. Telemedicine with its unique advantages holds the promise to grow exponentially in the future and is a compelling health-care segment to focus on for delivering health-care solution to the geographically distant consumers.

To explore the value in reminiscing about past festivals as a potential way of improving wellbeing in socially isolated times.

The paper uses previous research on reminiscence, nostalgia and wellbeing to underpin the analysis of self-recorded memory narratives. These were gathered from 13 pairs of festivalgoers during Covid-19 restrictions and included gathering their individual memories and their reminiscences together. The participant pairs were a mix of friends, family and couples who had visited festivals in the UK, Finland and Denmark.

Four key areas that emerged through the analysis were the emotions of nostalgia and anticipation, and the processes of reliving emotions and bonding through memories.

Future studies could take a longitudinal approach to see how memory sharing evolves and the impact of this on wellbeing. The authors also recommend undertaking similar studies in other cultural settings.

This study findings have implications for both post-festival marketing and for the further development of reminiscence therapy interventions.

The method provides a window into memory sharing that has been little used in previous studies. The narratives confirm the value in sharing memories and the positive impact this has on wellbeing. They also illustrate that this happens through positive forms of nostalgia that centre on gratitude and lead to hope and optimism. Anticipation, not emphasised in other studies, was also found to be important in wellbeing and was triggered through looking back at happier times.

Automatic modulation recognition (AMR) is a challenging problem in intelligent communication systems and has wide application prospects. At present, although many AMR methods based on deep learning have been proposed, the methods proposed by these works cannot be directly applied to the actual wireless communication scenario, because there are usually two kinds of dilemmas when recognizing the real modulated signal, namely, long sequence and noise. This paper aims to effectively process in-phase quadrature (IQ) sequences of very long signals interfered by noise.

This paper proposes a general model for a modulation classifier based on a two-layer nested structure of long short-term memory (LSTM) networks, called a two-layer nested structure (TLN)-LSTM, which exploits the time sensitivity of LSTM and the ability of the nested network structure to extract more features, and can achieve effective processing of ultra-long signal IQ sequences collected from real wireless communication scenarios that are interfered by noise.

Experimental results show that our proposed model has higher recognition accuracy for five types of modulation signals, including amplitude modulation, frequency modulation, gaussian minimum shift keying, quadrature phase shift keying and differential quadrature phase shift keying, collected from real wireless communication scenarios. The overall classification accuracy of the proposed model for these signals can reach 73.11%, compared with 40.84% for the baseline model. Moreover, this model can also achieve high classification performance for analog signals with the same modulation method in the public data set HKDD_AMC36.

At present, although many AMR methods based on deep learning have been proposed, these works are based on the model’s classification results of various modulated signals in the AMR public data set to evaluate the signal recognition performance of the proposed method rather than collecting real modulated signals for identification in actual wireless communication scenarios. The methods proposed in these works cannot be directly applied to actual wireless communication scenarios. Therefore, this paper proposes a new AMR method, dedicated to the effective processing of the collected ultra-long signal IQ sequences that are interfered by noise.

This paper aims to develop a novel grey Bernoulli model with memory characteristics, which is designed to dynamically choose the optimal memory kernel function and the length of memory dependence period, ultimately enhancing the model's predictive accuracy.

This paper enhances the traditional grey Bernoulli model by introducing memory-dependent derivatives, resulting in a novel memory-dependent derivative grey model. Additionally, fractional-order accumulation is employed for preprocessing the original data. The length of the memory dependence period for memory-dependent derivatives is determined through grey correlation analysis. Furthermore, the whale optimization algorithm is utilized to optimize the cumulative order, power index and memory kernel function index of the model, enabling adaptability to diverse scenarios.

The selection of appropriate memory kernel functions and memory dependency lengths will improve model prediction performance. The model can adaptively select the memory kernel function and memory dependence length, and the performance of the model is better than other comparison models.

The model presented in this article has some limitations. The grey model is itself suitable for small sample data, and memory-dependent derivatives mainly consider the memory effect on a fixed length. Therefore, this model is mainly applicable to data prediction with short-term memory effect and has certain limitations on time series of long-term memory.

In practical systems, memory effects typically exhibit a decaying pattern, which is effectively characterized by the memory kernel function. The model in this study skillfully determines the appropriate kernel functions and memory dependency lengths to capture these memory effects, enhancing its alignment with real-world scenarios.

Based on the memory-dependent derivative method, a memory-dependent derivative grey Bernoulli model that more accurately reflects the actual memory effect is constructed and applied to power generation forecasting in China, South Korea and India.

This paper discusses the effects of enabling conditions of project knowledge management in building volatile organizational memory. The theoretical rationale underlies a recursive relationship among enabling conditions of project knowledge management, organizational learning and memory.

This research employs a qualitative descriptive single case study approach to examine a mobile application development project undertaken by a major software company in Brazil. The analysis focuses on the project execution using an abductive analytical framework. The study data were collected through in-depth interviews and company documents.

Based on the research findings, the factors that facilitate behavior and strategy in managing project knowledge pose a challenge when it comes to fostering organizational learning. While both these factors play a role in organizational learning, the exchange of information from previous experience could be strengthened, and the feedback from the learning process could be improved. These shortcomings arise from emotional tensions that stem from power struggles within knowledge hierarchies.

Based on the research, it is recommended that project-structured organizations should prioritize an individual’s professional experience to promote organizational learning. Organizations with well-defined connections between their projects and strategies can better establish interconnections among knowledge creation, sharing and coding.

The primary contribution is to provide a comprehensive view that incorporates the conditions required to manage project knowledge, organizational learning and memory. The findings lead to four propositions that relate to volatile memory, intuitive knowledge, learning and knowledge encoding.

Rotating machinery is a crucial component of large equipment, and detecting faults in it accurately is critical for reliable operation. Although fault diagnosis methods based on deep learning have been significantly developed, the existing methods model spatial and temporal features separately and then weigh them, resulting in the decoupling of spatiotemporal features.

The authors propose a spatiotemporal long short-term memory (ST-LSTM) method for fault diagnosis of rotating machinery. The authors collected vibration signals from real rolling bearing and gearing test rigs for verification.

Through these two experiments, the authors demonstrate that machine learning methods still have advantages on small-scale data sets, but our proposed method exhibits a significant advantage due to the simultaneous modeling of the time domain and space domain. These results indicate the potential of the interactive spatiotemporal modeling method for fault diagnosis of rotating machinery.

The authors propose a ST-LSTM method for fault diagnosis of rotating machinery. The authors collected vibration signals from real rolling bearing and gearing test rigs for verification.

Limited by the types of sensors, the state information available for musculoskeletal robots with highly redundant, nonlinear muscles is often incomplete, which makes the control face a bottleneck problem. The aim of this paper is to design a method to improve the motion performance of musculoskeletal robots in partially observable scenarios, and to leverage the ontology knowledge to enhance the algorithm’s adaptability to musculoskeletal robots that have undergone changes.

A memory and attention-based reinforcement learning method is proposed for musculoskeletal robots with prior knowledge of muscle synergies. First, to deal with partially observed states available to musculoskeletal robots, a memory and attention-based network architecture is proposed for inferring more sufficient and intrinsic states. Second, inspired by muscle synergy hypothesis in neuroscience, prior knowledge of a musculoskeletal robot’s muscle synergies is embedded in network structure and reward shaping.

Based on systematic validation, it is found that the proposed method demonstrates superiority over the traditional twin delayed deep deterministic policy gradients (TD3) algorithm. A musculoskeletal robot with highly redundant, nonlinear muscles is adopted to implement goal-directed tasks. In the case of 21-dimensional states, the learning efficiency and accuracy are significantly improved compared with the traditional TD3 algorithm; in the case of 13-dimensional states without velocities and information from the end effector, the traditional TD3 is unable to complete the reaching tasks, while the proposed method breaks through this bottleneck problem.

In this paper, a novel memory and attention-based reinforcement learning method with prior knowledge of muscle synergies is proposed for musculoskeletal robots to deal with partially observable scenarios. Compared with the existing methods, the proposed method effectively improves the performance. Furthermore, this paper promotes the fusion of neuroscience and robotics.

The purpose of this study is to investigate the thermomechanical condition on the shape memory property of Polybutylene adipate-co-terephthalate (PBAT). PBAT is a widely researched and rapidly developed biodegradable copolyester. In a tensile test, we found that the fractured PBAT samples had a heat-driven shape memory effect which piqued our interest, and it will lay a foundation for the application of PBAT in new fields (such as heat shrinkable film).

The shape memory effect of PBAT and the effect of the thermomechanical condition on its shape memory property were confirmed and systematically investigated by a thermal mechanical analyzer and tensile machine.

The results showed that the PBAT film had broad shape memory transform temperature and exhibited excellent thermomechanical stability and shape memory properties. The shape memory fixity ratio (Rf) of the PBAT films was increased with the prestrain temperature and prestrain, where the highest Rf exceeded 90%. The shape memory recovery ratio (Rr) of the PBAT films was increased with the shape memory recovery temperature and decreased with the prestrain value, and the highest Rr was almost 100%. Moreover, the PBAT films had high shape memory recovery stress which increased with the prestrain value and decreased with the prestrain temperature, and the highest shape memory recovery stress can reach 7.73 MPa.

The results showed that PBAT had a broad shape memory transform temperature, exhibited excellent thermomechanical stability and shape memory performance, especially for the sample programmed at high temperature and had a larger prestrian, which will provide a reference for the design, processing and application of PBAT-based heat shrinkable film and smart materials.

This study confirmed and systematically investigated the shape memory effect of PBAT and the effect of the thermomechanical condition on the shape memory property of PBAT.

This paper aims to propose an improved version of portfolio optimization model through the prediction of the future behavior of stock returns using a combined wavelet-based long short-term memory (LSTM).

First, data are gathered and divided into two parts, namely, “past data” and “real data.” In the second stage, the wavelet transform is proposed to decompose the stock closing price time series into a set of coefficients. The derived coefficients are taken as an input to the LSTM model to predict the stock closing price time series and the “future data” is created. In the third stage, the mean-variance portfolio optimization problem (MVPOP) has iteratively been run using the “past,” “future” and “real” data sets. The epsilon-constraint method is adapted to generate the Pareto front for all three runes of MVPOP.

The real daily stock closing price time series of six stocks from the FTSE 100 between January 1, 2000, and December 30, 2020, is used to check the applicability and efficacy of the proposed approach. The comparisons of “future,” “past” and “real” Pareto fronts showed that the “future” Pareto front is closer to the “real” Pareto front. This demonstrates the efficacy and applicability of proposed approach.

Most of the classic Markowitz-based portfolio optimization models used past information to estimate the associated parameters of the stocks. This study revealed that the prediction of the future behavior of stock returns using a combined wavelet-based LSTM improved the performance of the portfolio.